before-you-claim SKILL.md skillA
before-you-claim from aleksandarbisevac/claude-plugins is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add aleksandarbisevac/claude-plugins/before-you-claim@git:20260913.fc83c3cPins git:20260913.fc83c3c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- aleksandarbisevac/claude-plugins
- Path
.claude/skills/before-you-claim/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260913.fc83c3c, committed Sep 13, 2026
- First version recorded
- Sep 12, 2026
- Size
- 8,436 bytes
- Repository stars
- 4
- License
- MIT
Seven questions answered with evidence at the moment a change is written, one for each defect class this repo's fault register keeps recording — a sentence claiming what the code does not do, a check that cannot fail, a fix for the instance while the class stays open, a rule that lives in prose with no mechanism, a property measured once, a guard that reads a command's spelling instead of its operation, a number written into prose. Use this skill every time you add or edit a comment, a…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Before you claim Every defect class below was written by an agent that had read the rules and was following them; the moment of writing had no question. This skill is the question — seven of them, each answered with something that can be *shown*. It holds no rule of its own: `no-silent-pass`, `writing-python` and `CLAUDE.md` say how; this asks *did you, on this change, and where is the evidence?* **Questions 1, 2, 5 and 7 are one line each because the evals said so.** Run against a baseline with no skill on 2026-09-12, twice and on two models, the arms tied on those four at full marks and separated on question 4 both times. They still get asked; they no longer get a paragraph. The runs and their grading are in `../before-you-claim-workspace/iteration-4/benchmark.json`. ## Two touches **Before the first edit**, one line: which questions this change will have to answer (`touches: 1, 3, 4`). The sweep, the mutation and the second measurement are cheap before the edit and expensive after; naming the question is what gets them done while they are cheap. **Before you say done**, the `claims:` block (shape at the end) — one line per question, each …
Read the whole file at its exact version.
How to install
mdr add aleksandarbisevac/claude-plugins/before-you-claim@sha256:3dd382de5f1be8f4The line at the top of this page pins the label git:20260913.fc83c3c, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_szg3k5hd2gur7mo3)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 12, 2026 and Sep 13, 2026, more than one a day.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260913.fc83c3c latest | 2026-09-13 | fc83c3c | 8,436 B | A | view · diff |
| git:20260912.ffff70c | 2026-09-12 | ffff70c | 7,754 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (8436 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
aleksandarbisevac/claude-plugins · 4 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_szg3k5hd2gur7mo3 GET https://markdownregistry.com/api/v1/resolve?ref=aleksandarbisevac/claude-plugins/before-you-claim GET https://markdownregistry.com/api/v1/blob/3dd382de5f1be8f47381b2a1a953188d7d4e327ad3de56d35c755c77ed6baa70
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.